Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 903
    Prev
    Next
    INDEX
    Explanations

    information about species and their distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [][]
    -0.48
    opsis
    -0.46
     zucchini
    -0.45
    CompilerServices
    -0.45
     "_"
    -0.43
     pro
    -0.43
    optera
    -0.42
     lượt
    -0.42
     irány
    -0.42
     conclu
    -0.41
    POSITIVE LOGITS
    EDEFAULT
    0.86
    ValueStyle
    0.83
    mybatisplus
    0.77
     cherchés
    0.75
    ьаж
    0.71
    RegressionTest
    0.70
     Archiproducts
    0.67
    
    0.66
    habits
    0.66
     snippetHide
    0.65
    Activations Density 0.461%

    No Known Activations